© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11289
    Prev
    Next
    INDEX
    Explanations

    subjective language

    oai_token-act-pair · gemini-2.0-flash

    moderate adjectives

    np_token-act-pair-logits · gpt-4o-mini

    slightly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !*\
    -0.65
    runApp
    -0.57
    __':
    -0.56
    urlpatterns
    -0.55
     Référence
    -0.54
    MarshalTo
    -0.53
     препратки
    -0.53
    gdx
    -0.52
     للمعارف
    -0.52
    جغرافيا
    -0.52
    POSITIVE LOGITS
     bit
    1.60
     slightly
    1.59
     somewhat
    1.50
    slightly
    1.41
     Slightly
    1.41
     biraz
    1.30
    Slightly
    1.30
     lidt
    1.30
    somewhat
    1.29
     nieco
    1.27
    Activations Density 1.402%

    No Known Activations